© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128017
    Prev
    Next
    INDEX
    Explanations

    Punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     azonban
    -1.80
     of
    -1.52
     أيض
    -1.48
    桖
    -1.48
     összefoglal
    -1.46
     celta
    -1.45
    Akhir
    -1.44
    président
    -1.42
    gląda
    -1.41
    嗞
    -1.38
    POSITIVE LOGITS
     to
    2.20
     —
    1.60
    CHOOL
    1.59
     were
    1.48
     I
    1.45
     ทำ
    1.43
     we
    1.40
     вентиля
    1.36
    owany
    1.35
    GING
    1.34
    Activations Density 0.144%

    No Known Activations